Vidlizer MCP Server
vidlizer
PyPI
v0.2.19
Published by arizawan — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
Point it at a video, image, or PDF — get structured JSON. Runs local (Ollama, LM Studio, oMLX) or cloud (OpenRouter). CLI + MCP server for Claude Code, Cursor, and Claude Desktop.
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 7 = 93. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 11
high Shell/command execution in server code (vidlizer/bootstrap.py)MTC-SRC-002
In the server's implementation (`vidlizer/bootstrap.py:15`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: via Homebrew…") r = subprocess.run(["brew", "install", pkg], capture_output=True, text=True) if r.returncode !=
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server vidlizer/bootstrap.py
high Shell/command execution in server code (vidlizer/cli.py)MTC-SRC-002
In the server's implementation (`vidlizer/cli.py:237`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: try: r = subprocess.run( ["osascript", "-e", 'POSIX path of (choose file with prompt "Sel
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server vidlizer/cli.py
high Shell/command execution in server code (vidlizer/detect.py)MTC-SRC-002
In the server's implementation (`vidlizer/detect.py:48`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: d" try: r = subprocess.run(["ffmpeg", "-version"], capture_output=True, text=True) line = r.stdout.s
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server vidlizer/detect.py
high Shell/command execution in server code (vidlizer/downloader.py)MTC-SRC-002
In the server's implementation (`vidlizer/downloader.py:71`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: tmpl, url] r = subprocess.run(cmd, capture_output=True, text=True) if r.returncode != 0: ra
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server vidlizer/downloader.py
high Shell/command execution in server code (vidlizer/frames.py)MTC-SRC-002
In the server's implementation (`vidlizer/frames.py:81`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: inner="dots2"): subprocess.run(cmd, check=True) frames = sorted(out_dir.glob("f_*.jpg")) if ts_file.ex
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server vidlizer/frames.py
high Shell/command execution in server code (vidlizer/preflight.py)MTC-SRC-002
In the server's implementation (`vidlizer/preflight.py:35`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: eo), ] result = subprocess.run(cmd, capture_output=True, text=True) info: dict = {"duration_s": None, "width
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server vidlizer/preflight.py
high Shell/command execution in server code (vidlizer/transcribe.py)MTC-SRC-002
In the server's implementation (`vidlizer/transcribe.py:17`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: udio stream.""" r = subprocess.run( ["ffprobe", "-v", "quiet", "-select_streams", "a:0", "-show_ent
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server vidlizer/transcribe.py
medium Hardcoded egress to an external endpoint (vidlizer/detect.py)MTC-SRC-003
In the server's implementation (`vidlizer/detect.py:99`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: "" try: r = requests.get( "https://openrouter.ai/api/v1/models", headers={"Authoriza
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server vidlizer/detect.py
medium Hardcoded egress to an external endpoint (vidlizer/models.py)MTC-SRC-003
In the server's implementation (`vidlizer/models.py:276`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: K try: r = requests.get( "https://openrouter.ai/api/v1/models", headers={"Authoriza
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server vidlizer/models.py
low Shell/command execution in packaging/dev tooling (tests/test_cli.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_cli.py:67`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: p_exits_zero(): r = subprocess.run( [sys.executable, "-m", "vidlizer.cli", "--help"], capture_output
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tests/test_cli.py
low Shell/command execution in packaging/dev tooling (tests/test_youtube.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_youtube.py:49`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: .parent.parent) r = subprocess.run( [sys.executable, "-m", "vidlizer.cli", _YT_URL, "-o", str(out),
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server tests/test_youtube.py
Tools 12
Each tool and what it can reach — statically extracted from the published source.
analyze_videono sensitive capabilityclear_usage_statsno sensitive capabilitydelete_analysisno sensitive capabilityget_full_analysisno sensitive capabilityget_phaseno sensitive capabilityget_stepno sensitive capabilityget_stepsno sensitive capabilityget_summaryno sensitive capabilityget_transcriptno sensitive capabilityget_usage_statsno sensitive capability
Show 2 more tools ↓
list_analysesno sensitive capabilitysearch_analysisno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (12 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 1
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v0.2.19 latest |
A 93/100 | 11 | 1.13.0 | 2026-08-25 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan vidlizer --online --registry pypiMore in Design & Media
Turn designs into shipped parts: quote 3D printing, CNC, and decals, then check out.
Aleph's official SiliconFlow media-generation MCP server (image / video / TTS)
MCP server for image generation using Google Gemini AI
Ambience AI MCP Server - Generate images, videos, and audio through Model Context Protocol
MCP server exposing every endpoint of the AstroWay Calculation API as tools — natal, synastry, transits, Vedic dashas, Tarot, Numerology, Human Design, AI horoscopes — for Claude Desktop, Cursor and any MCP-compatible AI agent.
Audio-guide and trip-planning tools for 1,100+ cities from Audiala. Free, no API key.